Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hv0905/nekoimagegallery
An AI-powered natural language & reverse Image Search Engine powered by CLIP & qdrant.
https://github.com/hv0905/nekoimagegallery
clip computer-vision image-search image-search-engine search-engine transformers
Last synced: 6 days ago
JSON representation
An AI-powered natural language & reverse Image Search Engine powered by CLIP & qdrant.
- Host: GitHub
- URL: https://github.com/hv0905/nekoimagegallery
- Owner: hv0905
- License: agpl-3.0
- Created: 2023-12-08T13:09:44.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2024-08-21T12:58:45.000Z (4 months ago)
- Last Synced: 2024-12-08T05:12:59.366Z (14 days ago)
- Topics: clip, computer-vision, image-search, image-search-engine, search-engine, transformers
- Language: Python
- Homepage: https://image-insights.edgeneko.com/
- Size: 7.36 MB
- Stars: 90
- Watchers: 4
- Forks: 9
- Open Issues: 2
-
Metadata Files:
- Readme: readme.md
- License: LICENSE
Awesome Lists containing this project
README
# NekoImageGallery
[](https://github.com/hv0905/NekoImageGallery/actions)
[](https://codecov.io/gh/hv0905/NekoImageGallery)
[](https://codeclimate.com/github/hv0905/NekoImageGallery/maintainability)
[](https://hub.docker.com/r/edgeneko/neko-image-gallery)
An online AI image search engine based on the Clip model and Qdrant vector database. Supports keyword search and similar
image search.
[中文文档](readme_cn.md)
## ✨ Features
- Use the Clip model to generate 768-dimensional vectors for each image as the basis for search. No need for manual
annotation or classification, unlimited classification categories.
- OCR Text search is supported, use PaddleOCR to extract text from images and use BERT to generate text vectors for
search.
- Use Qdrant vector database for efficient vector search.
## 📷Screenshots
> The above screenshots may contain copyrighted images from different artists, please do not use them for other
> purposes.
## ✈️ Deployment
### 🖥️ Local Deployment
#### Choose a metadata storage method
##### Qdrant Database (Recommended)
In most cases, we recommend using the Qdrant database to store metadata. The Qdrant database provides efficient
retrieval performance, flexible scalability, and better data security.
Please deploy the Qdrant database according to
the [Qdrant documentation](https://qdrant.tech/documentation/quick-start/). It is recommended to use Docker for
deployment.
If you don't want to deploy Qdrant yourself, you can use
the [online service provided by Qdrant](https://qdrant.tech/documentation/cloud/).
##### Local File Storage
Local file storage directly stores image metadata (including feature vectors, etc.) in a local SQLite database. It is
only recommended for small-scale deployments or development deployments.
Local file storage does not require an additional database deployment process, but has the following disadvantages:
- Local storage does not index and optimize vectors, so the time complexity of all searches is `O(n)`. Therefore, if the
data scale is large, the performance of search and indexing will decrease.
- Using local file storage will make NekoImageGallery stateful, so it will lose horizontal scalability.
- When you want to migrate to Qdrant database for storage, the indexed metadata may be difficult to migrate directly.
#### Deploy NekoImageGallery
1. Clone the project directory to your own PC or server, then checkout to a specific version tag (like `v1.0.0`).
2. It is highly recommended to install the dependencies required for this project in a Python venv virtual environment.
Run the following command:
```shell
python -m venv .venv
. .venv/bin/activate
```
3. Install PyTorch. Follow the [PyTorch documentation](https://pytorch.org/get-started/locally/) to install the torch
version suitable for your system using pip.
> If you want to use CUDA acceleration for inference, be sure to install a CUDA-supported PyTorch version in this
step. After installation, you can use `torch.cuda.is_available()` to confirm whether CUDA is available.
4. Install other dependencies required for this project:
```shell
pip install -r requirements.txt
```
5. Modify the project configuration file inside `config/`, you can edit `default.env` directly, but it's recommended to
create a new file named `local.env` and override the configuration in `default.env`.
6. Run this application:
```shell
python main.py
```
You can use `--host` to specify the IP address you want to bind to (default is 0.0.0.0) and `--port` to specify the
port you want to bind to (default is 8000).
You can see all available commands and options by running `python main.py --help`.
7. (Optional) Deploy the front-end application: [NekoImageGallery.App](https://github.com/hv0905/NekoImageGallery.App)
is a simple web front-end application for this project. If you want to deploy it, please refer to
its [deployment documentation](https://github.com/hv0905/NekoImageGallery.App).
### 🐋 Docker Deployment
#### About docker images
NekoImageGallery's docker image are built and released on Docker Hub, including serval variants:
| Tags | Description | Latest Image Size |
|---------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `edgeneko/neko-image-gallery:`
`edgeneko/neko-image-gallery:-cuda`
`edgeneko/neko-image-gallery:-cuda12.1` | Supports GPU inferencing with CUDA12.1 | [)](https://hub.docker.com/r/edgeneko/neko-image-gallery) |
| `edgeneko/neko-image-gallery:-cuda11.8` | Supports GPU inferencing with CUDA11.8 | [)](https://hub.docker.com/r/edgeneko/neko-image-gallery) |
| `edgeneko/neko-image-gallery:-cpu` | Only supports CPU inferencing | [)](https://hub.docker.com/r/edgeneko/neko-image-gallery) |
Where `` is the version number or version alias of NekoImageGallery, as follows:
| Version | Description |
|-------------------|--------------------------------------------------------------------------------------------------------|
| `latest` | The latest stable version of NekoImageGallery |
| `v*.*.*` / `v*.*` | The specific version number (correspond to Git tags) |
| `edge` | The latest development version of NekoImageGallery, may contain unstable features and breaking changes |
In each image, we have bundled the necessary dependencies, `openai/clip-vit-large-patch14` model
weights, `bert-base-chinese` model weights and `easy-paddle-ocr` models to provide a complete and ready-to-use image.
The images uses `/opt/NekoImageGallery/static` as volume to store image files, mount it to your own volume or directory
if local storage is required.
For configuration, we suggest using environment variables to override the default configuration. Secrets (like API
tokens) can be provided by [docker secrets](https://docs.docker.com/engine/swarm/secrets/).
#### Prepare `nvidia-container-runtime` (CUDA users only)
If you want to use CUDA acceleration, you need to install `nvidia-container-runtime` on your system. Please refer to
the [official documentation](https://docs.docker.com/config/containers/resource_constraints/#gpu) for installation.
> Related Document:
> 1. https://docs.docker.com/config/containers/resource_constraints/#gpu
> 2. https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker
> 3. https://nvidia.github.io/nvidia-container-runtime/
#### Run the server
1. Download the `docker-compose.yml` file from repository.
```shell
# For cuda deployment (default)
wget https://raw.githubusercontent.com/hv0905/NekoImageGallery/master/docker-compose.yml
# For CPU-only deployment
wget https://raw.githubusercontent.com/hv0905/NekoImageGallery/master/docker-compose-cpu.yml && mv docker-compose-cpu.yml docker-compose.yml
```
2. Modify the docker-compose.yml file as needed
3. Run the following command to start the server:
```shell
# start in foreground
docker compose up
# start in background(detached mode)
docker compose up -d
```
### Upload images to NekoImageGallery
There are serval ways to upload images to NekoImageGallery
- Through the web interface: You can use the web interface to upload images to the server. The web interface is provided
by [NekoImageGallery.App](https://github.com/hv0905/NekoImageGallery.App). Make sure you have enabled the
**Admin API** and set your **Admin Token** in the configuration file.
- Through local indexing: This is suitable for local deployment or when the images you want to upload are already on the
server.
Use the following command to index your local image directory:
```shell
python main.py local-index
```
The above command will recursively upload all images in the specified directory and its subdirectories to the server.
You can also specify categories/starred for images you upload, see `python main.py local-index --help` for more
information.
- Through the API: You can use the upload API provided by NekoImageGallery to upload images. By using this method, the
server can prevent saving the image files locally but only store their URLs and metadata.
Make sure you have enabled the **Admin API** and set your **Admin Token** in the configuration file.
This method is suitable for automated image uploading or sync NekoImageGallery with external systems.
Checkout [API documentation](#-api-documentation) for more information.
## 📚 API Documentation
The API documentation is provided by FastAPI's built-in Swagger UI. You can access the API documentation by visiting
the `/docs` or `/redoc` path of the server.
## ⚡ Related Project
Those project works with NekoImageGallery :D
[](https://github.com/hv0905/NekoImageGallery.App)
[](https://github.com/pk5ls20/LiteLoaderQQNT-NekoImageGallerySearch)
[](https://github.com/pk5ls20/pk5ls20/nonebot-plugin-nekoimage)
## 📊 Repository Summary
## ♥ Contributing
There are many ways to contribute to the project: logging bugs, submitting pull requests, reporting issues, and creating
suggestions.
Even if you with push access on the repository, you should create a personal feature branches when you need them.
This keeps the main repository clean and your workflow cruft out of sight.
We're also interested in your feedback on the future of this project. You can submit a suggestion or feature request
through the issue tracker. To make this process more effective, we're asking that these include more information to help
define them more clearly.
## Copyright
Copyright 2023 EdgeNeko
Licensed under AGPLv3 license.